{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CTMIOPDYOM3LWH7TBZW3XQOWZE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aff1e76e1176bcd4c437e1ee6d98fa66c736cca4752221512a2e3708343b7093","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T00:33:08Z","title_canon_sha256":"975dc5ae5b508c19929347130645f3569d6bc3394b5cdcac8b6b2733492dbd10"},"schema_version":"1.0","source":{"id":"2202.06443","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06443","created_at":"2026-07-05T05:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06443v3","created_at":"2026-07-05T05:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06443","created_at":"2026-07-05T05:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"CTMIOPDYOM3L","created_at":"2026-07-05T05:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"CTMIOPDYOM3LWH7T","created_at":"2026-07-05T05:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"CTMIOPDY","created_at":"2026-07-05T05:15:22Z"}],"graph_snapshots":[{"event_id":"sha256:0700d603f226c406a68591f5f83f16d1585614e4f0044eb30b9ef19003e4a975","target":"graph","created_at":"2026-07-05T05:15:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.06443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative trajectory planning methods for automated vehicles can solve traffic scenarios that require a high degree of cooperation between traffic participants. However, for cooperative systems to integrate into human-centered traffic, the automated systems must behave human-like so that humans can anticipate the system's decisions. While Reinforcement Learning has made remarkable progress in solving the decision-making part, it is non-trivial to parameterize a reward model that yields predictable actions. This work employs feature-based Maximum Entropy Inverse Reinforcement Learning combine","authors_text":"J. Marius Z\\\"ollner, Karl Kurzer, Matthias Bitzer","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T00:33:08Z","title":"Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06443","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:19f7c97ed68635092922a58efbf40380ad0a66e6e775c167c8023e3e7d5fa7a2","target":"record","created_at":"2026-07-05T05:15:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aff1e76e1176bcd4c437e1ee6d98fa66c736cca4752221512a2e3708343b7093","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T00:33:08Z","title_canon_sha256":"975dc5ae5b508c19929347130645f3569d6bc3394b5cdcac8b6b2733492dbd10"},"schema_version":"1.0","source":{"id":"2202.06443","kind":"arxiv","version":3}},"canonical_sha256":"14d8873c787336bb1ff30e6dbbc1d6c92fa35eb38967166655e9458401b81979","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14d8873c787336bb1ff30e6dbbc1d6c92fa35eb38967166655e9458401b81979","first_computed_at":"2026-07-05T05:15:22.863531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:22.863531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JyQlKUTbXcv3oEpTE5WPqZrcp/oNJxAM4knhHXJau/hQFT6f88JuUPvVRDLweMmwN0NBRa1thXRtl1AtwHBSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:22.863972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06443","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19f7c97ed68635092922a58efbf40380ad0a66e6e775c167c8023e3e7d5fa7a2","sha256:0700d603f226c406a68591f5f83f16d1585614e4f0044eb30b9ef19003e4a975"],"state_sha256":"ef4347ed94d2d6aab8df9ebe24ddbc8e96d6ab1ca0cbba2dd17cda40ac778dfb"}